Improving diagnosing performance for malignant parotid gland tumors using machine learning with multifeatures based on diffusion-weighted magnetic resonance imaging.

In this study, the performance of machine learning in classifying parotid gland tumors based on diffusion-related features obtained from the parotid gland tumor, the peritumor parotid gland, and the contralateral parotid gland was evaluated. Seventy-eight patients participated in this study and underwent magnetic resonance diffusion-weighted imaging. Three regions of interest, including the parotid gland tumor, the peritumor parotid gland, and the contralateral parotid gland, were manually contoured for 92 tumors, including 20 malignant tumors (MTs), 42 Warthin tumors (WTs), and 30 pleomorphic adenomas (PMAs). We recorded multiple apparent diffusion coefficient (ADC) features and applied a machine-learning method with the features to classify the three types of tumors. With only mean ADC of tumors, the area under the curve of the classification model was 0.63, 0.85, and 0.87 for MTs, WTs, and PMAs, respectively. The performance metrics were improved to 0.81, 0.89, and 0.92, respectively, with multiple features. Apart from the ADC features of parotid gland tumor, the features of the peritumor and contralateral parotid glands proved advantageous for tumor classification. Combining machine learning and multiple features provides excellent discrimination of tumor types and can be a practical tool in the clinical diagnosis of parotid gland tumors.

JOURNAL CLUB: The Warthin Tumor Score: A Simple and Reliable Method to Distinguish Warthin Tumors From Pleomorphic Adenomas and Carcinomas.

OBJECTIVE: The objective of this article is to propose a Warthin tumor (WT) score to distinguish WTs from other parotid tumors. MATERIALS AND METHODS: The study included 78 patients with 92 histologically proven parotid tumors, including 42 WTs, 30 pleomorphic adenomas (PMAs), and 20 carcinomas. Echo-planar DW images were acquired. The WT score, which comprised the mean apparent diffusion coefficient (ADCM) and the SD of the ADC (ADCSD) of tumors, patient age, and patient sex, was used to predict WTs. The diagnostic performance of the WT score was evaluated using ROC analyses. Statistical significance was denoted by p < 0.05. RESULTS: With the use of optimized criteria, including an ADCM less than or equal to 1.016 × 10-3 mm2/s (WT score, 1), an ADCSD less than or equal to 0.1171 × 10-3 mm2/s (WT score, 1), patient age older than 49 years (WT score, 1), and male sex (WT score, 1), a WT score greater than 2 had a sensitivity, specificity, positive negative value, negative predictive value, and accuracy of 85.7%, 100.0%, 100.0%, 89.3%, and 93.4%, respectively. CONCLUSION: The WT score allows parotid WTs to be distinguished from PMAs and carcinomas with high accuracy.

Malignant peripheral nerve sheath tumor of the chest wall associated with neurofibromatosis: a case report.

Primary chest wall tumors are relatively rare and represent approximately 5% of all thoracic neoplasms. Malignant peripheral nerve sheath tumor (MPNST) is highly aggressive and occurs in the second or third decade of patients with neurofibromatosis type 1 (NF-1). The estimated incidence of MPNST in patients with NF-1 is 2-5% (general population, 0.001%). This neoplasm usually affects the extremities and rarely the thoracic cavity. We present a case of MPNST of the chest wall in a patient with NF-1 who developed local recurrence 5 months after complete surgical resection and postoperative adjuvant radiotherapy.

Upregulation of heme oxygenase-1 expression in gingiva after cyclosporin A treatment.

BACKGROUND: Heme oxygenase (HO)-1 is a stress-inducible protein that confers cytoprotection, but its role in gingiva during cyclosporin A (CsA) therapy is unknown. We used in vivo and in vitro models to investigate the expression of mRNA and protein for HO-1 in gingiva upon CsA treatment. METHODS: Twenty-six male Sprague-Dawley rats were assigned to two groups after the establishment of edentulous ridges. Rats in the CsA group received CsA, 30 mg/kg/day for 4 weeks, whereas control rats received mineral oil only. All rats were killed after 4 weeks, and the edentulous gingivae were excised. mRNA and protein expression of HO-1 in gingivae were determined using reverse transcription-polymerase chain reaction (RT-PCR) and immunohistochemistry (IHC), respectively. For the in vitro study, cultured human gingival fibroblasts were harvested after treatment with various concentrations of CsA, and HO-1 mRNA and protein expression were determined using RT-PCR and Western blotting, respectively. RESULTS: Mean gingival HO-1 mRNA expression was greater in the CsA group than in the control animals (P = 0.076). IHC staining for HO-1 protein was significantly greater in the gingivae of CsA-treated rats than in those of the control group. In fibroblast cultures, expression of HO-1 mRNA and protein also increased significantly after CsA treatment. CONCLUSION: CsA upregulates the gingival expression of HO-1, which may exert a cytoprotective effect.